Hackathon November 2021 - Group 2

library(dplyr)

package 㤼㸱dplyr㤼㸲 was built under R version 4.0.4
Attaching package: 㤼㸱dplyr㤼㸲

The following objects are masked from 㤼㸱package:stats㤼㸲:

    filter, lag

The following objects are masked from 㤼㸱package:base㤼㸲:

    intersect, setdiff, setequal, union

library(ggplot2)

package 㤼㸱ggplot2㤼㸲 was built under R version 4.0.4

library(tidyr)

package 㤼㸱tidyr㤼㸲 was built under R version 4.0.3

library(plotly)

package 㤼㸱plotly㤼㸲 was built under R version 4.0.5Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 methods overwritten by 'htmltools':
  method               from         
  print.html           tools:rstudio
  print.shiny.tag      tools:rstudio
  print.shiny.tag.list tools:rstudio
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attaching package: 㤼㸱plotly㤼㸲

The following object is masked from 㤼㸱package:ggplot2㤼㸲:

    last_plot

The following object is masked from 㤼㸱package:stats㤼㸲:

    filter

The following object is masked from 㤼㸱package:graphics㤼㸲:

    layout

Introduction

We have been given the task of exploring time series analysis as part of a hackathon. We have been given access to 3 datasets:

1. Data on COVID-19 (coronavirus) by Our World in Data

1. Data on COVID-19 (coronavirus) by Our World in Data

This data can be read in directly from GitHub using {readr}. The col_types have to be specified up front otherwise it doesn’t load correctly.

# Read in COVID data from GitHub with correct types
covid_df <- readr::read_csv(
  file = "https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/owid-covid-data.csv",
  col_types = "cccDdddddddddddddddddddddddddddddcddddddddddddddddddddddddddddddddd"
)

# Inspect it
head(covid_df)

There are many columns and groups but we are going to focus on United Kingdom with a subset of columns.

# Filter and subset columns
uk_covid_df <- covid_df %>% 
  filter(location == "United Kingdom") %>%
  # Rename some columns so they are either {col} or cumulative_{col}
  select(
    date, 
    cases = new_cases,
    cumulative_cases = total_cases,
    deaths = new_deaths, 
    cumulative_deaths = total_deaths, 
    excess_mortality, 
    cumulative_excess_mortality = excess_mortality_cumulative, 
    cumulative_excess_mortality_absolute = excess_mortality_cumulative_absolute)

# Inspect it
head(uk_covid_df)

Check the date range and also some quick plots of the {col}s and cumulative_{col}s.

# Print off a summary of the dates
print(paste("Start date of cases:",uk_covid_df %>% summarise(min(date)) %>% pull()))

[1] "Start date of cases: 2020-01-31"

print(paste("Start date of deaths:", uk_covid_df %>% filter(cumulative_deaths > 0) %>% summarise(min(date)) %>% pull()))

[1] "Start date of deaths: 2020-03-06"

print(paste("End date of cases:",uk_covid_df %>% summarise(max(date)) %>% pull()))

[1] "End date of cases: 2021-11-16"

print(paste("End date of deaths:", uk_covid_df %>% filter(cumulative_deaths > 0) %>% summarise(max(date)) %>% pull()))

[1] "End date of deaths: 2021-11-16"

# Chart the non-cumulative cols (not sure how you can have negative deaths)
p <- uk_covid_df %>% 
  select(-starts_with("cumulative_")) %>%
  pivot_longer(cols = -date, names_to = "measure", values_to = "count") %>%
  ggplot(aes(x = date, y = count)) +
  geom_line() +
  facet_wrap(facets = ~measure, ncol = 1, scales = "free_y")

ggplotly(p)

# Chart the cumulative cols (not sure how you can have negative deaths)
p <- uk_covid_df %>% 
  select(date, starts_with("cumulative_")) %>%
  pivot_longer(cols = -date, names_to = "measure", values_to = "count") %>%
  ggplot(aes(x = date, y = count, group = measure)) +
  geom_line() +
  facet_wrap(facets = ~measure, ncol = 1, scales = "free_y")

ggplotly(p)